Add test

changedetectionio/flask_app.py

@@ -1432,6 +1432,7 @@ def changedetection_app(config=None, datastore_o=None):
                                                                      )
                 # Use the last loaded HTML as the input
                 update_handler.fetcher.content = decompressed_data
+                update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
                 try:
                     changed_detected, update_obj, contents, text_after_filter = update_handler.run_changedetection(
                         watch=tmp_watch,

changedetectionio/model/__init__.py

@@ -18,6 +18,7 @@ class watch_base(dict):
             'check_count': 0,
             'check_unique_lines': False,  # On change-detected, compare against all history if its something new
             'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'content-type': None,
             'date_created': None,
             'extract_text': [],  # Extract text by regex after filters
             'extract_title_as_title': False,

changedetectionio/processors/text_json_diff/processor.py

@@ -207,7 +207,7 @@ class perform_site_check(difference_detection_processor):
             stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
 
         if watch.get('remove_duplicate_lines'):
-            stripped_text_from_html = '\n'.join(dict.fromkeys(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
+            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
 
         if watch.get('sort_text_alphabetically'):
             # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap

changedetectionio/static/js/watch-settings.js

@@ -34,6 +34,7 @@ function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
 
 function request_textpreview_update() {
     if (!$('body').hasClass('preview-text-enabled')) {
+        console.error("Preview text was requested but body tag was not setup")
         return
     }
 
@@ -77,20 +78,19 @@ $(document).ready(function () {
 
     const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
     $("#text-preview-inner").css('max-height', (vh-300)+"px");
+
+    // Realtime preview of 'Filters & Text' setup
     var debounced_request_textpreview_update = request_textpreview_update.debounce(100);
 
     $("#activate-text-preview").click(function (e) {
-        $(this).fadeOut();
         $('body').toggleClass('preview-text-enabled')
-
         request_textpreview_update();
 
-        $("#text-preview-refresh").click(function (e) {
-            request_textpreview_update();
-        });
-        $('textarea:visible').on('keyup blur', debounced_request_textpreview_update);
-        $('input:visible').on('keyup blur change', debounced_request_textpreview_update);
-        $("#filters-and-triggers-tab").on('click', debounced_request_textpreview_update);
+        const method = $('body').hasClass('preview-text-enabled') ? 'on' : 'off';
+        $("#text-preview-refresh")[method]('click', debounced_request_textpreview_update);
+        $('textarea:visible')[method]('keyup blur', debounced_request_textpreview_update);
+        $('input:visible')[method]('keyup blur change', debounced_request_textpreview_update);
+        $("#filters-and-triggers-tab")[method]('click', debounced_request_textpreview_update);
     });
 
 });

changedetectionio/tests/test_encoding.py

@@ -3,7 +3,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks
+from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 import pytest
 
 
@@ -38,6 +38,11 @@ def test_check_encoding_detection(client, live_server, measure_memory_usage):
     # Give the thread time to pick it up
     wait_for_all_checks(client)
 
+
+    # Content type recording worked
+    uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['content-type'] == "text/html"
+
     res = client.get(
         url_for("preview_page", uuid="first"),
         follow_redirects=True

changedetectionio/update_worker.py

@@ -491,6 +491,8 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
+                        update_obj['content-type'] = update_handler.fetcher.get_all_headers().get('content-type', '').lower()
+
                         # Mark that we never had any failures
                         if not watch.get('ignore_status_codes'):
                             update_obj['consecutive_filter_failures'] = 0